@article{codejudgeevalcanlargelanguagemodelsbe,
  title = {CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?},
  author = {Yuwei Zhao and Ziyang Luo and Yuchen Tian and Hongzhan Lin and Weixiang Yan and Annan Li and Jing Ma},
  year = {2024},
  eprint = {2408.10718},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.10718v2},
}